Eureka-Bench-Logs

This repository contains the logs from the Eureka ML Insights framework, as described in the [Github repository](https://github.com/microsoft/eureka-ml-insights).

Relevant links:
- Technical report - [Eureka: Evaluating and Understanding Large Foundation Models](https://arxiv.org/abs/2409.10566)
- Technical report - [Inference-Time Scaling for Complex Tasks: Where We Stand and What Lies Ahead](https://arxiv.org/abs/2504.00294)
- Technical report - [Phi-4-reasoning technical report](https://arxiv.org/abs/2504.21318)
- [Project Website](https://microsoft.github.io/eureka-ml-insights)

All logs are organized by benchmark, model family, and model name.

For any questions on the logs or evaluation code, please contact [e-mail].

本仓库收录了Eureka ML Insights框架的运行日志，相关细节可参阅其[GitHub仓库](https://github.com/microsoft/eureka-ml-insights)。

相关链接如下：
- 技术报告——《Eureka：大基础模型的评估与认知》（https://arxiv.org/abs/2409.10566）
- 技术报告——《复杂任务的推理时缩放：当前进展与未来展望》（https://arxiv.org/abs/2504.00294）
- 技术报告——《Phi-4-reasoning技术报告》（https://arxiv.org/abs/2504.21318）
- 项目官网（https://microsoft.github.io/eureka-ml-insights）

所有日志均按照评测基准、模型家族与模型名称进行分类编排。

若您对日志或评估代码有任何疑问，请联系邮箱[e-mail]。